{
  "architectures": [
    "UltravoxModel"
  ],
  "audio_latency_block_size": null,
  "audio_model_id": "openai/whisper-large-v3-turbo",
  "audio_token_index": 128256,
  "auto_map": {
    "AutoConfig": "ultravox_config.UltravoxConfig",
    "AutoModel": "ultravox_model.UltravoxModel"
  },
  "custom_pipelines": {
    "ultravox-pipeline": {
      "impl": "ultravox_pipeline.UltravoxPipeline",
      "pt": [
        "AutoModel"
      ],
      "tf": [],
      "type": "multimodal"
    }
  },
  "hidden_size": 4096,
  "ignore_index": -100,
  "initializer_range": 0.02,
  "llm_only_training": false,
  "model_type": "ultravox",
  "norm_init": 0.4,
  "pad_token_id": 128009,
  "projector_act": "swiglu",
  "projector_ln_mid": true,
  "stack_factor": 8,
  "text_config": {
    "_name_or_path": "meta-llama/Llama-3.1-8B-Instruct",
    "architectures": [
      "LlamaForCausalLM"
    ],
    "attention_bias": false,
    "attention_dropout": 0.0,
    "bos_token_id": 128000,
    "eos_token_id": [
      128001,
      128008,
      128009
    ],
    "head_dim": 128,
    "hidden_act": "silu",
    "hidden_size": 4096,
    "initializer_range": 0.02,
    "intermediate_size": 14336,
    "max_position_embeddings": 131072,
    "mlp_bias": false,
    "model_type": "llama",
    "num_attention_heads": 32,
    "num_hidden_layers": 32,
    "num_key_value_heads": 8,
    "pretraining_tp": 1,
    "rms_norm_eps": 1e-05,
    "rope_scaling": {
      "factor": 8.0,
      "high_freq_factor": 4.0,
      "low_freq_factor": 1.0,
      "original_max_position_embeddings": 8192,
      "rope_type": "llama3"
    },
    "rope_theta": 500000.0,
    "torch_dtype": "bfloat16",
    "use_cache": true,
    "vocab_size": 128256
  },
  "text_model_id": null,
  "torch_dtype": "bfloat16",
  "transformers_version": "4.51.3",
  "vocab_size": 128256
}